Enhancing Handwritten Digit Recognition Through Convolutional Neural Networks: A Comprehensive Study

Abstract

The development of a handwritten digit recognition system is the main subject of the discussion. In particular, the Convolution Neural Network (CNN) technique is used in the proposed topic. The MNIST dataset is used to create the model. The “Modified National Institute of Standards and Technology dataset” has 60,000 grayscale photographs, which are tiny squares, comprises of hand-written single digits between digit Zero and digit Nine and each measuring 28 by 28. Placing a handwritten digit picture among any one of ten classes corresponding to integer values from digit Zero to digit Nine, inclusively is the assignment here. The system employs a camera to take photos made up of images produced by the MNIST test data set and samples supplied by other authors. It then continually processes the images and updates the output every 0.5 seconds. Accuracy for top-performing models is typically 99.